[Badcase]: 相同的数据，微调时在qwen2.5 72B预训练模型上的loss是qwen2 72B的3倍，请问2.5除了数据变多了，其他有什么不一样吗

[boundles]

Model Series

Qwen2.5

What are the models used?

Qwen2.5-72B预训练模型

What is the scenario where the problem happened?

text to sql

Is this badcase known and can it be solved using avaiable techniques?

• [X] I have followed the GitHub README.
• [X] I have checked the Qwen documentation and cannot find a solution there.
• [X] I have checked the documentation of the related framework and cannot find useful information.
• [X] I have searched the issues and there is not a similar one.

Information about environment

OS: Ubuntu 22.04 Python: Python 3.11 GPUs: 8 x NVIDIA A100

Description

如标题所描述